Introducing Web Search on Amazon Bedrock for foundation model grounding

<p>When a foundation model needs to answer a question about last week’s earnings call, yesterday’s regulatory change, or this morning’s weather forecast, it needs knowledge it was never trained on. Grounding the model in current web knowledge closes that gap – whether it’s powering chatbots, coding assistants, CLI tools, or enterprise applications, grounding helps answer questions beyond the model’s training and reduces hallucinations. Traditionally, connecting a model to web knowledge required developers to identify, integrate, and maintain a third-party Web Search provider, a process that delays project timelines and introduces data residency risks and operational overhead.</p> <p>At AWS New York Summit 2026, we announced the <a href="https://aws.amazon.com/blogs/aws/announcing-web-search-on-amazon-bedrock-agentcore-ground-your-ai-agents-in-current-accurate-web-knowledge/" target="_blank" rel="noopener">general availability of Web Search on AgentCore</a>. Today, we are extending it further with the general availability of Web Search on <a href="https://aws.amazon.com/bedrock/" target="_blank" rel="noopener">Amazon Bedrock</a>. It is a server-side built-in tool that grounds model responses in current web knowledge. With Web Search, grounding becomes a native capability of Amazon Bedrock, with no third-party vendors to onboard, no external APIs to orchestrate, and no additional third party vendor security reviews to conduct.</p> <p>In this post, we walk through what Web Search on Amazon Bedrock is, why it matters, how to enable it using the OpenAI Responses API, and how to get started with the tool.</p> <h2 id="what-web-search-on-bedrock-provides">What Web Search on Amazon Bedrock provides</h2> <p>Web Search is designed for Amazon Bedrock model inference, with the following differentiators:</p> <p><strong>Multi-source grounding approach:</strong> Web Search is backed by a web index that Amazon operates, spanning billions of documents and refreshed continually. It combines this index with a built-in knowledge graph that anchors the entities in a domain along with the connections between them. When a question is factual in nature; say, who wrote a particular book or what year an event took place; Web Search uses the knowledge graph to answer with strong confidence, rather than leaving the model to infer the answer from extracted page text. That can help cut down on the small factual inaccuracies that tend to slip in whenever an agent assembles an answer from fragments on its own.</p> <p><strong>Context-efficient retrieval.</strong> Rather than handing the model a raw page and hoping it finds the relevant part, Web Search performs semantic snippet extraction – pulling the passages from each web page that bear on the query and returning them in a form optimized for the model’s context window. The model sees the parts that matter, with fewer tokens spent on boilerplate. Retrieval is fast, so grounded responses can be delivered with minimal latency.</p> <p><strong>Single-parameter enablement.</strong> Web Search becomes a single parameter in your existing OpenAI-compatible API call, removing the need for vendor onboarding, API keys, orchestration layers, and separate SDKs.</p> <p><strong>Helping with enterprise-grade compliance out of the box.</strong> By default, Web Search on Bedrock offers zero data egress, so your data never leaves your AWS environment. As we introduce new capabilities, some future features may expose data only at your explicit request. For the latest information, please refer to the Amazon Bedrock documentation . Web Search operates entirely within Amazon Bedrock’s infrastructure, supporting customers’ compliance requirements.</p> <h2 id="how-it-works">How it works</h2> <p><img src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/17/ML-21265-1.png" alt="Diagram of the Web Search request lifecycle: the model identifies a knowledge gap, Bedrock formulates a query,